Biometric Authentication Using Multi-Biosignal Consistency Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current biometric authentication technologies face challenges in verifying that biometric features are generated from a real living body, as they can be forged or copied, leading to potential unauthorized access.

Innovation Solution

A method that extracts and compares physiological features from multiple biosignals, such as ECG, facial images, and fingerprints, to determine if they are generated from the same living body by calculating consistent levels based on properties like time domain, frequency domain, and statistical properties, using machine learning techniques to enhance authentication reliability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If multiple biosignals are captured and compared to verify living body authenticity, then the reliability of authentication is improved, but the device complexity and measurement difficulty increase

Engineering Contradiction:
Improveauthentication reliabilityVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the authentication process into distinct modules: biosignal capture module, physiological feature extraction module, consistency analysis module, and authentication decision module. Each module handles a specific task, making the complex system manageable and maintainable while achieving high reliability through multi-signal verification

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent employs multiple biosignals (ECG, PPG, EEG, EMG, EOG, RESP) that can be captured simultaneously or sequentially from the same sensor array. This multi-functional approach allows the system to verify living body authenticity through various physiological parameters, enhancing reliability without requiring entirely separate systems for each signal type

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Reliability

If multiple physiological features are extracted and compared, then the difficulty of forging biometric features increases, but the measurement precision requirements and processing complexity increase

Engineering Contradiction:
Improveanti-forgery capacityVSAvoidfeature extraction precision
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The patent extracts multiple types of physiological features from the same biosignals, including time-domain features (heart rate, respiration rate), frequency-domain features (spectral analysis of ECG/EEG), and statistical features (variance, skewness). By analyzing the same signal through different parameter domains, the system increases anti-forgery capacity while managing measurement precision through established signal processing techniques

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system incorporates consistency analysis that compares extracted physiological features across multiple biosignals and provides feedback for authentication decisions. This feedback mechanism verifies whether features from different signals are consistent with each other, making forgery detection more robust without requiring extremely high measurement precision for individual features

Inventive Principle:
Principle #23Feedback

3Reliability

If biosignals are captured for a predetermined period to ensure accuracy, then the authentication reliability is improved, but the loss of time increases

Engineering Contradiction:
Improveauthentication accuracyVSAvoidauthentication time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent performs preliminary processing of biosignals including filtering, baseline correction, and artifact removal during the capture phase. By preparing the data in advance, the system reduces the time needed for detailed analysis later, maintaining high authentication accuracy while minimizing overall processing time

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system captures biosignals for predetermined periods at strategically chosen intervals rather than continuously. This periodic sampling approach ensures sufficient data for accurate physiological feature extraction while avoiding unnecessary time loss from prolonged continuous monitoring, balancing accuracy requirements with time efficiency

Inventive Principle:
Principle #19Periodic action

Data Source

PatentEP3037036B1Biometric authentication method and apparatus
Publication Date: 2021.01.06 SAMSUNG ELECTRONICS CO LTD
  • EP3037036B1 patent drawingFigure 1
  • EP3037036B1 patent drawingFigure 2
  • EP3037036B1 patent drawingFigure 3

AI summary

A biometric authentication apparatus and method are provided. The biometric authentication apparatus may obtain at least two types of biosignals, extract a same type of physiological features from each of the biosignals, and determine whether the biosignals are generated from a same living body based on the extracted same type of physiological features.